Page 87 - eBook_Proceedings of the International Conference on Digital Manufacturing V1

Leveraging Machine Learning to Enhance Supply Chain Agility and Strategic
Operational Excellence

model using random forest algorithm. Finally, the model was able
to have an accuracy of 98%.

This research methodology addresses the supply chain
inefficiencies effectively. By incorporating advanced machine
learning algorithms, the results optimise supply chain, predict
accurate demands, reduce cost, and minimise delays. The results
concluded that Random Forest was the most effective algorithm
to predict demand for the dataset used, achieving 98% accuracy
on the industry dataset. To bring further advancement, it is
recommended that future studies focus on integrating IoT and
implement advanced machine learning algorithms, like
Reinforcement Learning, to ensure real-time decision making.
Reinforcement learning would also help in taking into account
complex environment factors which cannot be handled by XG
Boost and Random Forest effectively.

CONCLUSION

This study effectively demonstrates how machine learning
algorithms can optimise supply chain management for demand
forecasting. We found notable increases in predicted accuracy by
continuously testing and improving models, especially with the
Random Forest algorithm on actual data from the ABC Industry.
The model is the most dependable of the examined models, with
an exceptional R2 value of 0.989, a 98% accuracy in pending
demand. Using datasets from multiple sources, such as industry
datasets and Kaggle, allowed for a thorough study that connect
theoretical understanding with real-world applications.

The procedure brought to light the difficulties in managing
noisy and imperfect data as well as the significance of choosing
the right algorithms for a given dataset. Even if previous models
like XG Boost performed well in some situations, Random Forest
outperformed them because of its better feature management and
resilience to over fitting. This research highlights how machine
learning may improve supply chain efficiency through better
resource allocation, lower operational costs, predicts more

71